Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1793 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9020. Min Range: -2.9020
Max Act: 2.9020. Min Act: -0.1700
Data Index: 637231 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9020. Min Range: -2.9020
Max Act: 2.8225. Min Act: -0.1700
Data Index: 759833 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9020. Min Range: -2.9020
Max Act: 2.8384. Min Act: -0.1700
Data Index: 189469 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9020. Min Range: -2.9020
Max Act: 2.8066. Min Act: -0.1700
Data Index: 1178271 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9020. Min Range: -2.9020
Max Act: 2.8225. Min Act: -0.1700
Data Index: 55142 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9020. Min Range: -2.9020
Max Act: 2.7907. Min Act: -0.1700
Data Index: 531538 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9020. Min Range: -2.9020
Max Act: 2.7907. Min Act: -0.1700
Data Index: 971609 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9020. Min Range: -2.9020
Max Act: 2.8066. Min Act: -0.1700
Data Index: 1145980 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9020. Min Range: -2.9020
Max Act: 2.7748. Min Act: -0.1700
Data Index: 9494 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9020. Min Range: -2.9020
Max Act: 2.7748. Min Act: -0.1700
Data Index: 814712 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9020. Min Range: -2.9020
Max Act: 2.7748. Min Act: -0.1700
Data Index: 148592 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9020. Min Range: -2.9020
Max Act: 2.7588. Min Act: -0.1700
Data Index: 956309 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9020. Min Range: -2.9020
Max Act: 2.7907. Min Act: -0.1700
Data Index: 35951 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9020. Min Range: -2.9020
Max Act: 2.7588. Min Act: -0.1700
Data Index: 1088591 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9020. Min Range: -2.9020
Max Act: 2.7748. Min Act: -0.1700
Data Index: 896407 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9020. Min Range: -2.9020
Max Act: 2.7907. Min Act: -0.1700
Data Index: 354942 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9020. Min Range: -2.9020
Max Act: 2.7588. Min Act: -0.1700
Data Index: 665071 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9020. Min Range: -2.9020
Max Act: 2.7428. Min Act: -0.1700
Data Index: 1040416 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9020. Min Range: -2.9020
Max Act: 2.7588. Min Act: -0.1700
Data Index: 1109411 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9020. Min Range: -2.9020
Max Act: 2.7588. Min Act: -0.1700
Data Index: 969531 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19